Patent Grant
10331089
The embodiments described herein relate in general to the field of power generation. More specifically, the embodiments described herein relate to systems and methodologies for forecasting the generation of solar power.
There is a great interest in replacing or augmenting electric power generation by using solar power. Solar power is the conversion of sunlight into electricity, typically using photovoltaic cells or concentrated solar power. An advantage of solar power is the removal of the need to discover, mine, or drill for fossil fuel sources and lower emissions. A disadvantage of solar power is that the output of a solar power plant varies based on the availability of sunlight. The availability of sunlight changes based on time of year (there is less sunlight available in the winter than in the summer), time of day (there is no sunlight available at night), and weather (cloud cover reduces the level of available sunlight).
Embodiments are directed to a computer-implemented method of forecasting power generation. The method includes analyzing, using a processor, a set of historical weather data. A set of historical power generation data is analyzed using the processor. The processor then determines a plurality of clusters, where each cluster of the plurality of clusters represents weather data for a time period and power generated during the time period. The processor then receives a weather forecast for a future time period. The processor determines which cluster of the set of cluster contains weather data that is most similar to the weather forecast. The processor then uses the historical power generation data of the cluster to forecast power generation for the future time period.
Embodiments are further directed to a computer system for forecasting power generation. The system includes a memory and a processor system communicatively coupled to the memory. The processor is configured to perform a method that includes analyzing a set of historical weather data. Then a set of historical power generation data is analyzed. A plurality of clusters is determined, where each cluster of the plurality of clusters represents weather data for a time period and power generated during the time period. A weather forecast is received for a future time period. The method then determines which cluster of the set of cluster contains weather data that is most similar to the weather forecast. Then, the historical power generation data of the cluster is used to forecast power generation for the future time period.
Embodiments are further directed to a computer program product for displaying a presentation. The computer program product includes a computer-readable storage medium having program instructions embodied therewith, wherein the computer-readable storage medium is not a transitory signal per se. The program instructions are readable by a processor system to cause the processor system to perform a method that includes analyzing a set of historical weather data. Then a set of historical power generation data is analyzed. A plurality of clusters is determined, where each cluster of the plurality of clusters represents weather data for a time period and power generated during the time period. A weather forecast is received for a future time period. The method then determines which cluster of the set of cluster contains weather data that is most similar to the weather forecast. Then, the historical power generation data of the cluster is used to forecast power generation for the future time period.
Additional features and advantages are realized through techniques described herein. Other embodiments and aspects are described in detail herein. For a better understanding, refer to the description and to the drawings.
The subject matter which is regarded as embodiments is particularly pointed out and distinctly claimed in the claims at the conclusion of the specification. The foregoing and other features and advantages of the embodiments are apparent from the following detailed description taken in conjunction with the accompanying drawings in which:
In the accompanying figures and following detailed description of the embodiments, the various elements illustrated in the figures are provided with three digit reference numbers
Various embodiments of the present invention will now be described with reference to the related drawings. Alternate embodiments can be devised without departing from the scope of this invention. Various connections might be set forth between elements in the following description and in the drawings. These connections, unless specified otherwise, can be direct or indirect, and the present description is not intended to be limiting in this respect. Accordingly, a coupling of entities can refer to either a direct or an indirect connection.
Additionally, although a detailed description of a computing device is presented, configuration and implementation of the teachings recited herein are not limited to a particular type or configuration of computing device(s). Rather, embodiments are capable of being implemented in conjunction with any other type or configuration of wireless or non-wireless computing devices and/or computing environments, now known or later developed.
Furthermore, although a detailed description of presentation algorithms is included herein, implementation of the teachings recited herein are not limited to embodiments described herein. Rather, embodiments are capable of being implemented in conjunction with any other type of presentation system, now known or later developed.
At least the features and combinations of features described in the immediately present application, including the corresponding features and combinations of features depicted in the figures amount to significantly more than implementing a method of forecasting power generation based on weather forecasts. Additionally, at least the features and combinations of features described in the immediately preceding paragraphs, including the corresponding features and combinations of features depicted in the figures go beyond what is well understood, routine and conventional in the relevant field(s).
Electrical power is generated at power plants, transmitted, distributed and sold via an electric grid to locations throughout the world. Power plants use a variety of energy sources to generate electricity. The most widely used energy sources are coal, natural gas, nuclear power, hydroelectric power, wind, and solar. Because of the constant increase in power consumption throughout the world, there is an ever-increasing need for the generation of electrical power. Environmental concerns have led to the lessening of popularity of the use fossil fuels (such as coal and natural gas) as an energy source and an increase in the popularity of other energy sources. Nuclear power has its own environmental concerns, so there is increasing interest in using renewable energy sources such as solar energy.
Solar power plants convert incoming sunlight into electricity. Such a conversion can occur in a variety of ways, including the use of photovoltaics or the use of concentrated solar power to power a heat engine (such as a steam turbine) that is coupled to an electrical power generator.
One issue that occurs with solar power is that the power generated by a solar power plant can vary due to factors that are beyond human control. While fossil fuel power plants, nuclear power plants, and hydroelectric power plants can have a maximum power generation capacity, the amount that is actually generated can be controlled by humans by controlling the amount of fuel being consumed or the amount of water flowing across a turbine connected to an electrical power generator. In contrast, the maximum amount of power being generated by a solar energy power plant or a wind power plant at any given time is dependent on several factors that are beyond the control of humans (a solar energy power plant can produce less power than its full capacity merely by turning off or disconnecting some of the photovoltaic cells). These factors can include the time of day (more sunlight is available at certain times of day than others, including night time when a negligible amount of sunlight is available), time of year (there is less sunlight available in the winter than there is in the summer), and weather conditions (there is less sunlight available in cloudy weather or rainy weather than in sunny weather).
An electrical power company or utility that uses solar power will often supplement the electrical power with other power sources. The other power sources can be internal to the electrical power company (such as a fossil fuel or hydroelectric plant operated by the electrical power company), or they can be external to the electrical power company, in which case the electrical power company will purchase power from a marketplace in order to supplement the power generated by the solar energy power plant. To be able to purchase or use power to supplement a solar energy power plant, an electrical power company should be able to forecast how much power will be generated by the solar energy power plant as well as how much power will be used by its customers.
Embodiments of the present invention address the above-described problem by using a novel method and system to analyze weather data to forecast the amount of electrical power that will be generated by the solar energy power plant. Based on historical weather and solar power data, a solar power profile is trained or created with a plurality of clusters, each cluster representing an exemplary power profile that estimates electrical power produced in a certain time period for a given weather condition. Then, given a weather forecast, an embodiment can predict the cluster to which the weather forecast will belong, based on prior weather data. Finally, using the historical power generation of the cluster to which the weather forecast belongs, an embodiment determines a forecast the solar power being generated for the time period in question.
Because forecasting weather is very unpredictable, it has been found that previously used methods of using weather forecasts to forecast solar power generation are inaccurate. One concept that can be used to create improved estimates is the use of “clusters” of historical data. With reference to
Each graph represents a cluster of historical data. A cluster of data means a group of days that have a similar profile of power generated over time. The clusters shown in
One concept used in some embodiments is that each day (or other time period for which a weather forecast is available) can be estimated to fall within one of the clusters presented in
Although the use of eight clusters is illustrated in
Method 200 is an overview of a general method and is presented in
A set of historical weather data is loaded into a system (block 202). The historical weather data can contain many types of data. In some embodiments, different pieces of weather data can be loaded into a system for comparison purposes. The data can include traditional weather data such as air temperature, water temperature, humidity, dew point, wind speed, wind direction, cloud cover, barometric pressure, precipitation, pollen count, pollutant count, and the like. Statistical data regarding the same also can be accepted as input or calculated (such as mean, maximum, median, standard deviation, and rate of change). In some embodiments, up to 40 or more pieces of weather data can be used as input. A set of historical solar power generation data is loaded into the system (block 204). The historical solar power generation covers the same time period as the historical weather data is loaded. The data for both weather and solar power generation can be periodic data. As more time periods are used for each day, a more accurate daily power profile results. In some embodiments, the weather and solar power generation information can be hourly. In some embodiments, the weather and solar power generation information can be more often (such as every 30 minutes, or 15 minutes, or 5 minutes). Any number of pieces of data can be used, with the tradeoff being that more data increases the complexity of the calculations that will be performed.
For each time period in the data sets, the weather data is associated with corresponding power generation data (block 206).
Once the power generation data and weather data is matched, clusters can be formed (block 208). The number of clusters formed can be adjusted based on the desired accuracy weighed against the computational complexity of the calculations. The clusters are grouped by similarity, with similarity being defined in further detail below. A supervised machine-learning algorithm can be used for such a purpose. An advantage of such an algorithm is that the algorithm improves each time that it is executed, because the algorithm improves each time there is more data with which to work.
Any type of machine learning algorithm can be used to generate the clusters. In some embodiments, a non-linear machine-learning algorithm is used. In some embodiments, the non-linear machine-learning algorithm is a support vector machine (SVM) algorithm. In some embodiments, it might be found that a gradient boosting machine (GBM) algorithm result in more accurate results. In other embodiments, other machine-learning algorithm might be found to be the most effective. In general, a machine-learning algorithm operates by taking known values of weather data and corresponding values of the power generation data. Then an algorithm iteratively goes through the data for each time period to find an approximate relationship between the weather data and the power generation data. Any one of a variety of machine learning techniques (or combination thereof) can be used to create the clusters.
Once the clusters are generated, the training portion can be considered complete and operation can begin for daily usage. However, it should be understood that the above-described blocks can be executed each time more data is available (such as when each time period has passed). Such an iterative process can result in a more accurate formation of clusters.
For daily (or other appropriate time period) usage, a weather forecast is received (block 210). The weather forecast can include quantities such as temperature, humidity, wind speed, wind direction, cloud cover, barometric pressure, precipitation, and the like. The weather forecast can be for any time period. In some embodiments, the time period is three days, with forecast data provided in hourly increments. In some embodiments, other time periods and frequency of data is used.
The weather forecast is compared against the previously generated clusters (block 212). Each cluster includes historical weather data and historical power generation data. For each cluster, the historical weather data can be summarized. In some embodiments, the summary of historical weather data can include a mean hourly value for each weather aspect being tracked (e.g., temperature, humidity, wind speed, wind direction, cloud cover, barometric pressure, precipitation, and the like), as well as other statistical values.
Comparing the weather forecast includes finding the cluster that most closely matches the weather forecast. The comparison can be performed using a similarity calculation, such as the similarity calculations set forth in further detail below. For each cluster, a similarity score is calculated that compares the cluster with the weather forecast. The cluster with the highest similarity score is the cluster that is most similar to the weather forecast. The comparison can be performed using a supervised machine-learning algorithm. In such a manner, the forecast data can be stored for later use on future days, along with actual weather data and actual power generation data.
The comparison to previously generated clusters results in the day of the forecast being placed in one of the clusters. Thereafter, using the cluster data along with other data (such as the time of year to determine how long the sun will be up), an estimated solar power generation forecast is calculated (block 214). This can be performed in any one of a number of manners. For example, a cluster can include data for one of many different time periods, such as an hourly forecast for how much electrical power will be generated for each hour. The time periods can be set to as fine a granularity as is needed to create a desired level of precision. In other words, once it has been found that the weather forecast for a particular date is most similar to graph 120 (for example), it is estimated that the power generation for that day also follows graph 120. The estimate of power generation can be adjusted for any change to the set of photovoltaics in question.
Once the solar power forecast is generated, it can be determined how much supplemental power is needed. For example, an electrical power company typically has an estimate of how much electrical power will be needed for a particular day. This can be estimated from prior usage, weather forecasts, day of the week, and the like, in a manner now known in the art or developed in the future. Once the power usage estimate is determined, the amount of supplemental power can be determined by subtracting the power usage estimate from the power generation estimate. The electrical power utility can then arrange to have the amount of supplemental power estimated. This can be performed by buying supplemental power from other utilities, or by using other sources of power that are available to the electrical power utility.
The concept of similarity will now be described. Similarity can be calculated in any of a variety of different manners. In some embodiments, similarity can be calculated as the product of the complexity measure of the daily power profile and the Euclidean distance of the daily power profile. In equation form, this can be expressed as shown below in Equation (1):
D(Xi, Xj)=CF(Xi, Xj)·d(Xi, Xj)
Here, D represents the similarity score for a certain time period, CF represents the complexity measure, and d represents the Euclidian distance. Xi and Xj are the two data points being compared, one for the ith time period and one for the jth time period. In the embodiment shown in
The time period can be of one of a variety of different durations. In some embodiments, a power profile can be calculated for an entire day. In some embodiments, smaller time increments can be used in an attempt to create forecasts of greater precision.
The complexity measure is defined as shown below in Equation (2):
Here, CE represents the change from time period to time period as defined below in Equation (3):
CE(Xi)=√{square root over (Σt=1n(Xti−Xt+1i)2)}
The Euclidean distance is defined below in Equation (4):
d(Xi, Xj)=√{square root over (Σt=1n(Xti−Xt+1j)2)}
While the above description refers to the use of weather forecasts to determine solar power forecasts, it should be understood that embodiments are not so limited. Any type of power generation that is dependent on weather, such as wind power generation, can use an embodiment.
Computer system 300 includes one or more processors, such as processor 302. Processor 302 is connected to a communication infrastructure 304 (e.g., a communications bus, crossover bar, or network). Computer system 300 can include a display interface 306 that forwards graphics, textual content, and other data from communication infrastructure 304 (or from a frame buffer not shown) for display on a display unit 308. Computer system 300 also includes a main memory 310, preferably random access memory (RAM), and can also include a secondary memory 312. Secondary memory 312 can include, for example, a hard disk drive 314 and/or a removable storage drive 316, representing, for example, a floppy disk drive, a magnetic tape drive, or an optical disc drive. Hard disk drive 314 can be in the form of a solid-state drive (SSD), a traditional magnetic disk drive, or a hybrid of the two. There also can be more than one hard disk drive 314 contained within secondary memory 312. Removable storage drive 316 reads from and/or writes to a removable storage unit 318 in a manner well known to those having ordinary skill in the art. Removable storage unit 318 represents, for example, a floppy disk, a compact disc, a magnetic tape, or an optical disc, etc. which is read by and written to by removable storage drive 316. As will be appreciated, removable storage unit 318 includes a computer-readable medium having stored therein computer software and/or data.
In alternative embodiments, secondary memory 312 can include other similar means for allowing computer programs or other instructions to be loaded into the computer system. Such means can include, for example, a removable storage unit 320 and an interface 322. Examples of such means can include a program package and package interface (such as that found in video game devices), a removable memory chip (such as an EPROM, secure digital card (SD card), compact flash card (CF card), universal serial bus (USB) memory, or PROM) and associated socket, and other removable storage units 320 and interfaces 322 which allow software and data to be transferred from the removable storage unit 320 to computer system 300.
Computer system 300 can also include a communications interface 324. Communications interface 324 allows software and data to be transferred between the computer system and external devices. Examples of communications interface 324 can include a modem, a network interface (such as an Ethernet card), a communications port, or a PC card slot and card, a universal serial bus port (USB), and the like. Software and data transferred via communications interface 324 are in the form of signals that can be, for example, electronic, electromagnetic, optical, or other signals capable of being received by communications interface 324. These signals are provided to communications interface 324 via communication path (i.e., channel) 326. Communication path 326 carries signals and can be implemented using wire or cable, fiber optics, a phone line, a cellular phone link, an RF link, and/or other communications channels.
In the present description, the terms “computer program medium,” “computer usable medium,” and “computer-readable medium” are used to refer to media such as main memory 310 and secondary memory 312, removable storage drive 316, and a hard disk installed in hard disk drive 314. Computer programs (also called computer control logic) are stored in main memory 310 and/or secondary memory 312. Computer programs also can be received via communications interface 324. Such computer programs, when run, enable the computer system to perform the features discussed herein. In particular, the computer programs, when run, enable processor 302 to perform the features of the computer system. Accordingly, such computer programs represent controllers of the computer system. Thus it can be seen from the forgoing detailed description that one or more embodiments provide technical benefits and advantages.
Referring now to
Embodiments can be a system, a method, and/or a computer program product. The computer program product can include a computer-readable storage medium (or media) having computer-readable program instructions thereon for causing a processor to carry out aspects of embodiments of the present invention.
The computer-readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer-readable storage medium can be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of the computer-readable storage medium includes the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing. A computer-readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.
Computer-readable program instructions described herein can be downloaded to respective computing/processing devices from a computer-readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and/or a wireless network. The network can include copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge servers. A network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium within the respective computing/processing device.
Computer-readable program instructions for carrying out embodiments can include assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object-oriented programming language such as Smalltalk, C++ or the like, and conventional procedural programming languages, such as the “C” programming language or similar programming languages. The computer-readable program instructions can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) can execute the computer-readable program instructions by utilizing state information of the computer-readable program instructions to personalize the electronic circuitry, in order to perform embodiments of the present invention.
Aspects of various embodiments are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to various embodiments. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
These computer-readable program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions can also be stored in a computer-readable storage medium that can direct a computer, a programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable storage medium having instructions stored therein includes an article of manufacture including instructions which implement aspects of the function/act specified in the flowchart and/or block diagram block or blocks.
The computer-readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable apparatus, or other device implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams can represent a module, segment, or portion of instructions, which includes one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block can occur out of the order noted in the figures. For example, two blocks shown in succession can, in fact, be executed substantially concurrently, or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts or carry out combinations of special purpose hardware and computer instructions.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises” and/or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, element components, and/or groups thereof.
The corresponding structures, materials, acts, and equivalents of all means or step plus function elements in the claims below are intended to include any structure, material, or act for performing the function in combination with other claimed elements as specifically claimed. The descriptions presented herein are for purposes of illustration and description, but is not intended to be exhaustive or limited. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of embodiments of the invention. The embodiment was chosen and described in order to best explain the principles of operation and the practical application, and to enable others of ordinary skill in the art to understand embodiments of the present invention for various embodiments with various modifications as are suited to the particular use contemplated.
| Number | Name | Date | Kind |
|---|---|---|---|
| 9053439 | Marwah et al. | Jun 2015 | B2 |
| 20110276269 | Hummel | Nov 2011 | A1 |
| 20110282514 | Ropp et al. | Nov 2011 | A1 |
| 20120143856 | Klinkigt | Jun 2012 | A1 |
| 20120166085 | Gevorkian | Jun 2012 | A1 |
| 20140095076 | Marwah | Apr 2014 | A1 |
| 20150134251 | Bixel | May 2015 | A1 |
| 20150177415 | Bing | Jun 2015 | A1 |
| 20170286838 | Cipriani et al. | Oct 2017 | A1 |
| Number | Date | Country |
|---|---|---|
| 2013169903 | Nov 2013 | WO |
| Entry |
|---|
| Khabibrakhmanov, “Forecasting Solar Power Generation Using Real Time Power Data”, U.S. Appl. No. 15/288,707. |
| Lorenz, et al., “Irradiance Forecasting for the Power Prediction of Grid-Connected Photovoltaic Systems”, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 2, No. 1, Mar. 2009, 9 Pages, IEEE. |
| Khabibrakhmanov et al., “Forecasting Solar Power Generation Using Real-Time Power Data,” U.S. Appl. No. 15/288,707, filed Oct. 7, 2016. |
| List of IBM Patents or Patent Applications Treated as Related; Date Filed: Oct. 7, 2016, 2 pages. |
| Khabibrakhmanov et al., “Forecasting Solar Power Generation Using Real-Time Power Data,” U.S. Appl. No. 15/445,218, filed Feb. 28, 2017. |
| List of IBM Patents or Patent Applications Treated as Related; Date Filed: Dec. 27, 2017, 2 pages. |
| Number | Date | Country | |
|---|---|---|---|
| 20180101147 A1 | Apr 2018 | US |
